Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3658 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.0116. Min Range: -3.0116

Max Act: 3.0116. Min Act: -0.0000

Data Index: 858053 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 3.0116. Min Range: -3.0116

Max Act: 2.9612. Min Act: -0.0000

Data Index: 31080 (The Pile)

Max Activating Token Index: 938

Text #2

Max Range: 3.0116. Min Range: -3.0116

Max Act: 2.8544. Min Act: -0.0000

Data Index: 246548 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 3.0116. Min Range: -3.0116

Max Act: 2.5284. Min Act: -0.0000

Data Index: 118746 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 3.0116. Min Range: -3.0116

Max Act: 2.6628. Min Act: -0.0000

Data Index: 433292 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 3.0116. Min Range: -3.0116

Max Act: 2.3190. Min Act: -0.0000

Data Index: 1656554 (The Pile)

Max Activating Token Index: 777

Text #6

Max Range: 3.0116. Min Range: -3.0116

Max Act: 2.2564. Min Act: -0.0000

Data Index: 1289850 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 3.0116. Min Range: -3.0116

Max Act: 2.0942. Min Act: -0.0000

Data Index: 852142 (The Pile)

Max Activating Token Index: 129

Text #8

Max Range: 3.0116. Min Range: -3.0116

Max Act: 2.0331. Min Act: -0.0000

Data Index: 1236296 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 3.0116. Min Range: -3.0116

Max Act: 1.8226. Min Act: -0.0000

Data Index: 396610 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 3.0116. Min Range: -3.0116

Max Act: 2.0309. Min Act: -0.0000

Data Index: 1320252 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 3.0116. Min Range: -3.0116

Max Act: 1.8804. Min Act: -0.0000

Data Index: 276740 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 3.0116. Min Range: -3.0116

Max Act: 1.9573. Min Act: -0.0000

Data Index: 1686934 (The Pile)

Max Activating Token Index: 297

Text #13

Max Range: 3.0116. Min Range: -3.0116

Max Act: 1.8370. Min Act: -0.0000

Data Index: 776559 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 3.0116. Min Range: -3.0116

Max Act: 1.7398. Min Act: -0.0000

Data Index: 1217972 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 3.0116. Min Range: -3.0116

Max Act: 2.1443. Min Act: -0.0000

Data Index: 1147617 (The Pile)

Max Activating Token Index: 56

Text #16

Max Range: 3.0116. Min Range: -3.0116

Max Act: 1.8070. Min Act: -0.0000

Data Index: 1327580 (The Pile)

Max Activating Token Index: 239

Text #17

Max Range: 3.0116. Min Range: -3.0116

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1840651 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 3.0116. Min Range: -3.0116

Max Act: 1.7685. Min Act: -0.0000

Data Index: 108641 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 3.0116. Min Range: -3.0116

Max Act: 1.7609. Min Act: -0.0000

Data Index: 1507332 (The Pile)

Max Activating Token Index: 162